Luv VermaOptimizing LLMs: Best Practices (Prompt Engineering, RAG and Fine-tuning)Welcome to this blog, which is inspired by a recent talk on optimizing LLMs by OpenAI. This blog summarizes the effective strategies and…Jan 5Jan 5
Luv VermaUnpacking Transformers: A Deep Dive into the Full Architecture — Part 4In Part 3 of this series, we took a deep dive into concepts such as Positional Encodings, Multi-Head Attention, the addition of…May 13, 2023May 13, 2023
Luv VermaEvolving Self-Attention: Positional Encoding, Multi-Head, and Masked Attention — Transformers…In Part 2 of this series, we took a deep dive into naive-self attention, where we look into naive self-attention through equations and…May 13, 2023May 13, 2023
Luv VermaDiving Deep into Naive Self-Attention: A Step Towards Understanding Transformers, Part 2In Part 1 of this series, we took a deep dive into the fundamental concepts of ‘attention’ in the context of Sequence-to-Sequence (Seq2Seq)…May 13, 2023May 13, 2023
Luv VermaDemystifying Attention Mechanisms in Sequence-to-Sequence Models, Transformers (Part 1)Seq2seq models gained immense popularity but faced the bottleneck issue which was dealt with by the concepts from the transformers model…May 9, 2023May 9, 2023
Luv VermaOvercoming MapReduce Challenges: A Comparison with Apache Spark — BigData, Part 2IntroductionMay 1, 2023May 1, 2023
Luv VermaGaussian Mixture models (with a focus on soft-means clustering)Welcome to my blog on Gaussian Mixture Models and soft-means clustering (intuition developed using an image dataset). Throughout this…Apr 22, 2023Apr 22, 2023
Luv VermaGaining an Intuitive Understanding of 1-D and 2-D Gaussian Distributions Using Image ExamplesWelcome to this blog, where the aim is to provide an intuitive understanding of 1-D and 2-D Gaussian distributions, focusing on visual…Apr 21, 2023Apr 21, 2023
Luv VermaUnderstanding DDPM objective, Part 3Welcome to Part 3 of the exciting blog series, where we’ll dive deep into the world of diffusion models — a cutting-edge class of…Apr 12, 2023Apr 12, 2023